Using mutual information to design feature combinations

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Ellis, Daniel P W ^a   Bilmes, Jeff A ^b  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFIERS;

AMOUNT OF INFORMATION; COMBINATION STRATEGIES; COMBINATION SYSTEMS; CONDITIONAL MUTUAL INFORMATION; DESIGN FEATURES; INDEPENDENT CLASSIFIERS; MUTUAL INFORMATIONS; SPEECH RECOGNITION PERFORMANCE;

SPEECH RECOGNITION;

EID: 85009067484     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. S. Sharma, D. Ellis, S. Kajarekar, P. Jain and H. Hermansky, "Feature extraction using non-linear transformation for robust speech recognition on the Aurora database", Proc. ICASSP, Istanbul, II-1117-1120, June 2000.
2. A. Janin, D. Ellis and N. Morgan, "Multi-stream speech recognition: Ready for prime time?" Proc. Eurospeech-99, II-591-594, Budapest, September 1999.
3. K. Kirchoff and J. Bilmes, "Dynamic classifier combination in hybrid speech recognition systems using utterancelevel confidence values", Proc. ICASSP, Phoenix, II-693-696, May 1999.
4. J. Billa, T. Colhurst, A. El-Jaroudi, R. Iyer, K. Ma, S. Matsoukas, C. Quillen, F. Richardson, M. Siu, G. Zavaliagkos, H. Gish, "Recent Experiments in Large Vocabulary Conversational Speech Recognition", Proc. ICASSP, Phoenix, May 1999.
5. S. Wu, B. Kingsbury, N. Morgan and S. Greenberg, "Incorporating Information from Syllable-length Time Scales into Automatic Speech Recognition", Proc. ICASSP, Seattle, 721-724, 1998.
6. D. Ellis, "Stream combination before and/or after the acoustic model", ICSI Technical Report TR-00-007 http://www.icsi.berkeley.edu/techreports.
7. D. Pearce, Aurora Project: Experimental framework for the performance Evaluation of distributed speech recognition front-ends, ETSI working paper, September 1998.
8. B. Kingsbury, Perceptually-inspired Signal Processing Strategies for Robust Speech Recognition in Reverberant Environments, Ph. D. dissertation, Dept. of EECS, University of California, Berkeley, 1998.
9. N. Morgan and H. Bourlard, "Continuous Speech Recognition: An Introduction to the Hybrid HMM/Connectionist Approach." Signal Processing Magazine, 25-42, May 1995.
10. J. Bilmes, "Maximum mutual information based reduction strategies for cross-correlation based joint distributional modeling", Proc. ICASSP, Seattle, 469-472, April 1998.
11. J. Bilmes, Natural Statistical Models for Automatic Speech Recognition, Ph. D. Dissertation, Dept. of EECS, University of California, Berkeley, May 1999.